lkml.org 
[lkml]   [2005]   [Apr]   [11]   [last100]   RSS Feed
Views: [more markup]  [less markup]  [headers]  [forward] 
 
Messages in this thread
/
DateMon, 11 Apr 2005 11:33:42 -0500
FromTroy Benjegerdes <>
SubjectRe: [PATCH][RFC][0/4] InfiniBand userspace verbs implementation
On Mon, Apr 11, 2005 at 08:34:19AM -0700, Roland Dreier wrote:
>     Troy> How is memory pinning handled? (I haven't had time to read
>     Troy> all the code, so please excuse my ignorance of something
>     Troy> obvious).
> 
> The userspace library calls mlock() and then the kernel does
> get_user_pages().

Is there a check in the kernel that the memory is actually mlock()ed?

What if a malicious (or broken) application does ibv_reg_mr() but
doesn't lock the memory? Does the IB card get a physical address for a
page that might get swapped out?

>     Troy> The old mellanox drivers used to have a hack to call
>     Troy> 'sys_mlock', and promiscuously lock memory any old userspace
>     Troy> application asked for. What is the API for the new uverbs
>     Troy> memory registration, and how will things like memory hotplug
>     Troy> and NUMA page migration be able to unpin pages locked by a
>     Troy> user program?
> 
> The API for uverbs memory registration is ibv_reg_mr(), and right now
> the memory is pinned and that's it.
> 
>  - R.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-04-11 18:45    [from the cache]
©2003-2008